ROIAL: Region of Interest Active Learning for Characterizing Exoskeleton Gait Preference Landscapes

TL;DR

This paper introduces ROIAL, an active learning framework that efficiently characterizes individual exoskeleton gait preferences by learning utility landscapes from limited, safe, and preference-based feedback, aiding personalized gait optimization.

Contribution

ROIAL is a novel active learning method that models user gait preferences through preference feedback, improving safety and efficiency in characterizing utility landscapes.

Findings

ROIAL accurately predicts individual gait utility landscapes.

The framework identifies key gait parameters influencing user preferences.

It demonstrates feasibility with limited human trials.

Abstract

Characterizing what types of exoskeleton gaits are comfortable for users, and understanding the science of walking more generally, require recovering a user's utility landscape. Learning these landscapes is challenging, as walking trajectories are defined by numerous gait parameters, data collection from human trials is expensive, and user safety and comfort must be ensured. This work proposes the Region of Interest Active Learning (ROIAL) framework, which actively learns each user's underlying utility function over a region of interest that ensures safety and comfort. ROIAL learns from ordinal and preference feedback, which are more reliable feedback mechanisms than absolute numerical scores. The algorithm's performance is evaluated both in simulation and experimentally for three non-disabled subjects walking inside of a lower-body exoskeleton. ROIAL learns Bayesian posteriors that predict each exoskeleton user's utility landscape across four exoskeleton gait parameters. The algorithm discovers both commonalities and discrepancies across users' gait preferences and identifies the gait parameters that most influenced user feedback. These results demonstrate the feasibility of recovering gait utility landscapes from limited human trials.